ClawHub
Back to skill

Security audit

AWS Infra

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AWS CLI helper that can access cloud account data, but its instructions are coherent, read-first, and require confirmation before changes.

Install only if you are comfortable letting the agent use your local AWS CLI identity to inspect AWS resources. Use least-privilege AWS profiles, prefer read-only roles for routine questions, and require careful review before approving any command that changes, deletes, scales, or modifies IAM, billing, or production resources.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
Use the local AWS CLI to answer questions about AWS resources. Default to read‑only queries. Only propose or run write/destructive actions after explicit user confirmation.

## Quick Start
1. Determine profile/region from environment or `~/.aws/config`.
2. Start with identity:
   - `aws sts get-caller-identity`
3. Use read‑only service commands to answer the question.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
Use the local AWS CLI to answer questions about AWS resources. Default to read‑only queries. Only propose or run write/destructive actions after explicit user confirmation.

## Quick Start
1. Determine profile/region from environment or `~/.aws/config`.
2. Start with identity:
   - `aws sts get-caller-identity`
3. Use read‑only service commands to answer the question.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
See `references/aws-cli-queries.md` for common command patterns.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/aws-cli-queries.md (reported line 46)May include surrounding context.

md
## Common write actions (confirm before running)
- Scale ECS service: `aws ecs update-service --cluster <cluster> --service <svc> --desired-count N`
- Update ASG: `aws autoscaling update-auto-scaling-group --auto-scaling-group-name <name> --desired-capacity N`
- S3 delete: `aws s3 rm s3://bucket/key`

Static analysis

No suspicious patterns detected.